🏗️ Building on HF

Melvin Vivas

melvindave

2 27 198

https://www.donvitocodes.com

AI & ML interests

AI Engineer — Specializing in AI Agents, Local/Open-source models, and AI workflows implementation.

Recent Activity

updated a collection about 5 hours ago

Small Models

liked a Space about 5 hours ago

LiquidAI/LFM2.5-VL-3B-WebGPU

liked a model 5 days ago

Qwen/Qwen3.8-27B

View all activity

Organizations

updated a collection about 5 hours ago

Small Models

Collection

2 items • Updated about 5 hours ago

liked a Space about 5 hours ago

LFM2.5-VL-3B WebGPU

💧

Run LFM2.5-VL-3B locally in your browser with WebGPU

liked a model 5 days ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 4 days ago • 666k • • 11k

updated a collection 5 days ago

Language Models (Reasoning)

Collection

6 items • Updated 5 days ago

liked a model 5 days ago

meta-models/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated 7 days ago • 384k • • 1.67k

upvoted an article 5 days ago

Article

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

CohereLabs

•

6 days ago

• 35

liked a model 8 days ago

unsloth/Muse-Glimmer-30B-GGUF

Image-Text-to-Text • 28B • Updated 8 days ago • 787k • 475

replied to their post 9 days ago

thank you @John6666 .this is really helpful!

upvoted an article 9 days ago

Article

Deploy local agents everywhere with LFM2.5-2.6B

LiquidAI

•

14 days ago

• 90

liked a model 10 days ago

LiquidAI/LFM2.5-2.6B

Text Generation • 3B • Updated 11 days ago • 154k • 656

posted an update 10 days ago

Post

What's the best small model for training on tool calls?

Basically, the use case is to use it with an agent which processes a customer's inquiry and suggest a travel itinerary via an API call. I'm thinking this will just be wrapped as a tool call). It should be smart enough also to understand when to call multiple tools to achieve its goal.

Any ideas on this? I need to do a POC with a small model which can run in my RTX 3090. Planning to use unsloth for the fine-tune.

Just wanted to know which model I can use as baseline for this use case.